We report on the automatic alignment of a transmission electron microscope equipped with an orbital angular momentum sorter using a convolutional neural network. The neural network is able to control all relevant parameters of both the electron-optical setup of the microscope and the external voltage source of the sorter without input from the user. It can compensate for mechanical and optical misalignments of the sorter, in order to optimize its spectral resolution. The alignment is completed over a few frames and can be kept stable by making use of the fast fitting time of the neural network.

Solid oxide fuel cells (SOFCs) are promising candidates for use in alternative energy technologies. A full understanding of the reaction mechanisms in these dynamic material systems is required to optimize device performance and overcome present limitations. Here, we show that in situ transmission electron microscopy (TEM) can be used to study redox reactions and ionic conductivity in SOFCs in a gas environment at elevated temperature. We examine model ultrathin half and complete cells in two environmental TEMs using off-axis electron holography and electron energy-loss spectroscopy. Our results from the model cells provide insight into the essential phenomena that are important for the operation of commercial devices. Changes in the activities of dopant cations in the solid electrolyte are detected during oxygen anion conduction, demonstrating the key role of dopants in electrolyte architecture in SOFCs.